Early Risk Prediction of Fibromyalgia using Symptom Lifestyle Features and Machine Learning Models

DOI

10.2991/978-94-6239-616-6_50How to use a DOI?

Keywords

Fibromyalgia; early prediction; lifestyle indicators; WPI; SSS; Random Forest; Gradient Boosting; XGBoost; explainable AI; health informatics

Abstract

Fibromyalgia (FM) is a heterogeneous, multi-symptom disorder whose early recognition is hampered by symptom overlap with other conditions and reliance on subjective reports. This paper systematically reviews 25 studies (2015–2025) and proposes an integrated ML framework for early FM risk stratification that fuses self-reported symptom scores, lifestyle indicators, and physiological signals. Methodology: structured literature search, comparative extraction of datasets/features/algorithms, and experimental comparison of Logistic Regression, Random Forest and XGBoost with class-imbalan ce handling. Key findings: ensemble models (XGBoost) performed best (AUC ≈ 0.85–0.90) and stress, sleep quality and fatigue were the most consistent predictors across studies. Main gap: lack of large-scale, multimodal longitudinal datasets and limited external validation. We conclude with a taxonomy of ML methods and targeted future directions (federated learning, wearables, XAI) to accelerate clinical translation.

Copyright

© 2026 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - S. Balaji
AU  - S. Agilavani
AU  - B. Madhumithra
AU  - M. Kaviya
PY  - 2026
DA  - 2026/03/31
TI  - Early Risk Prediction of Fibromyalgia using Symptom Lifestyle Features and Machine Learning Models
BT  - Proceedings of the International Conference on Artificial Intelligence and Secure Data Analytics (ICAISDA 2025)
PB  - Atlantis Press
SP  - 663
EP  - 684
SN  - 1951-6851
UR  - https://doi.org/10.2991/978-94-6239-616-6_50
DO  - 10.2991/978-94-6239-616-6_50
ID  - Balaji2026
ER  -